A Fit-and-Merge Algorithm for Range-Image Segmentation and Model Reconstruction

2002 ◽  
Vol 2 (4) ◽  
pp. 285-293 ◽  
Author(s):  
M. Djebali ◽  
M. Melkemi ◽  
N. Sapidis
Keyword(s):  
Image Segmentation ◽  
Polynomial Approximation ◽  
Region Growing ◽  
Reconstruction Algorithm ◽  
Theoretical Work ◽  
Range Image ◽  
Model Reconstruction ◽  
Industrial Data ◽  
Merging Procedure ◽  
Principal Surfaces

A segmentation and model-reconstruction algorithm is proposed based on polynomial approximation and on a new version of the “region growing” methodology. First, an initial partition is calculated on the basis of differential-geometric properties of the range image. Then, the first merging procedure is applied (“merge with constraints”) aiming at correctly identifying principal surfaces of the model. It examines all possible mergers of regions and selects those satisfying strict compatibility constraints. The second merging procedure relaxes these constraints to produce the “extended” regions and surfaces of the final segmentation. Theoretical work is presented proving the consistency of these merging procedures. Finally, application of the algorithm on industrial data is presented demonstrating the efficiency of the proposed methodology.

scholarly journals Objectness Supervised Merging Algorithm for Color Image Segmentation

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Haifeng Sima ◽  
Aizhong Mi ◽  
Zhiheng Wang ◽  
Youfeng Zou
Keyword(s):  
Image Segmentation ◽  
Color Image ◽  
Region Growing ◽  
Color Image Segmentation ◽  
Semantic Features ◽  
Merging Procedure ◽  
Proposed Model ◽  
Merging Process ◽  
High Level ◽  
Color Texture

Ideal color image segmentation needs both low-level cues and high-level semantic features. This paper proposes a two-hierarchy segmentation model based on merging homogeneous superpixels. First, a region growing strategy is designed for producing homogenous and compact superpixels in different partitions. Total variation smoothing features are adopted in the growing procedure for locating real boundaries. Before merging, we define a combined color-texture histogram feature for superpixels description and, meanwhile, a novel objectness feature is proposed to supervise the region merging procedure for reliable segmentation. Both color-texture histograms and objectness are computed to measure regional similarities between region pairs, and the mixed standard deviation of the union features is exploited to make stop criteria for merging process. Experimental results on the popular benchmark dataset demonstrate the better segmentation performance of the proposed model compared to other well-known segmentation algorithms.

A HYBRID METHOD TOWARDS THE SEGMENTATION OF RANGE IMAGES FOR 3-D OBJECT RECOGNITION

1994 ◽  
Vol 08 (04) ◽  
pp. 969-995 ◽  
Author(s):  
DINESH P. MITAL ◽  
EAM KHWANG TEOH ◽  
ALAN W.T. LIM
Keyword(s):  
Image Segmentation ◽  
Object Recognition ◽  
Hybrid Approach ◽  
Region Growing ◽  
Object Identification ◽  
Range Image ◽  
Range Images ◽  
One Dimensional ◽  
Identification Process ◽  
Combine Region

This paper presents a hybrid approach towards accomplishing the task of range image segmentation. It tends to combine region growing and one-dimensional orthogonal polynomial fitting techniques for the detection of edges in range images. Edges detected by such a method possesses good localisation property. This aids to steer the region growing process towards accomplishing accurate border partitioning. In addition, the incorporation of region growing process eliminates internal micro edges and provides for missing border reconstruction as it is able to detect weak edges. It is believed that the edge and segmentation maps produced, when conveyed to the higher level recognition process, may prove valuable not only for CAD based modeling purposes but may also aid to provide descriptive syntax to the object identification process.

Towards distributed region growing image segmentation based on MapReduce

2015 ◽  
Author(s):  
P. N. Happ ◽  
R. S. Ferreira ◽  
G. A. O. P. Costa ◽  
R. Q. Feitosa ◽  
C. Bentes ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Region Growing

scholarly journals A smoke image segmentation algorithm based on rough set and region growing

2019 ◽  
Vol 65 (No. 8) ◽  
pp. 321-329
Author(s):  
Haitao Wang ◽  
Yanli Chen
Keyword(s):  
Image Segmentation ◽  
Rough Set ◽  
Region Growing ◽  
Recall Rate ◽  
Segmentation Algorithm ◽  
Colour Space ◽  
Seed Point ◽  
Black Smoke ◽  
Growth Method ◽  
Image Segmentation Algorithm

Because the image fire smoke segmentation algorithm can not extract white, gray and black smoke at the same time, a smoke image segmentation algorithm is proposed by combining rough set and region growth method. The R component of the image is extracted in the RGB colour space, the roughness histogram is constructed according to the statistical histogram of the R component, and the appropriate valley value in the roughness histogram is selected as the segmentation threshold, the image is roughly segmented. Relative to the background image, the smoke belongs to the motion information, and the motion region is extracted by the interframe difference method to eliminate static interference. Smoke has a unique colour feature, a smoke colour model is created in the RGB colour space, the motion disturbances of similar colour are removed and the suspected smoke areas are obtained. The seed point is selected in the region, and the region is grown on the result of rough segmentation, the smoke region is extracted. The experimental results show that the algorithm can segment white, gray and black smoke at the same time, and the irregular information of smoke edges is relatively complete. Compared with the existing algorithms, the average segmentation accuracy, recall rate and F-value are increased by 19%, 21.5% and 20%, respectively.<br /><br />

Pixel-parallel digital CMOS implementation of image segmentation by region growing

2005 ◽  
Vol 152 (6) ◽  
pp. 579 ◽  
Author(s):  
T. Morimoto ◽  
Y. Harada ◽  
T. Koide ◽  
H.J. Mattausch
Keyword(s):  
Image Segmentation ◽  
Region Growing ◽  
Digital Cmos ◽  
Cmos Implementation
Sign in / Sign up

Export Citation Format

Share Document